Emergent behaviours based on episodic encoding and familiarity driven retrieval
In analogy to animal research, where behavioural and internal neu-ral dynamics are simultaneously analysed, this paper suggests a method for emergent behaviours arising in interaction with the underlying neural mech-anism. This way an attempt to go beyond the indeterministic nature of the emergent behaviours of robots is made. The neural dynamics is represented as an interaction of memories of experienced episodes, the current environ-mental input and the feedback of previous motor actions. The emergent prop-erties can be observed in a two staged process: exploratory (latent) learning and goal oriented learning. Correspondingly, the learning is dominated to a different extent by two factors: novelty and reward. While the reward learn-ing is used to show the relevance of the method, the novelty/familiarity is a basis for forming the emergent properties. The method is strongly inspired by the state of the art understanding of the hippocampal functioning and espe-cially its role in novelty detection and episodic memory formation in relation to spatial context.
KeywordsEpisodic Memory Place Cell Emergent Behaviour Hebbian Learning Novelty Detection
Unable to display preview. Download preview PDF.
- 2.Eichenbaum, H., Dudchenko, P., Wood, E., Shapiro, M., Tanila, H.: The Hippocampus, Memory, and Place Cells: Is It Spatial Memory or a Memory Space? Neuron. Cell Press 23, 209–226 (1999)Google Scholar
- 9.Tulving, E., Donaldson, W.: Organization of memory. Acad. Press, New York (1972)Google Scholar
- 10.Barakova, E., Lourens, T.: Prediction of rapidly changing environmental dynamics for real time behaviour adaptation. In: Dynamic Perception, pp. 147–152. IOS press, Amsterdam (2002)Google Scholar
- 11.Pfeifer, R., Scheier, C.: Understanding Intelligence. MIT Press, Cambridge (1999)Google Scholar
- 12.O’Keefe, J., Nadel, L.: The Hippocampus as a Cognitive Map. Oxford Press (1971)Google Scholar
- 13.Schweighofer, N., Doya, K., Lay, F.: Unsupervised learning of granule cell sparse codes enhances cerebellar adaptive control. Neuro science 103, 35–50 (2002)Google Scholar
- 14.Zhang, L., Tao, H., Holt, C., Harris, W., Poo, M.: A critical window for cooperation and competition among developing retinotectal synapses. Nature 395 (1998)Google Scholar
- 18.Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)Google Scholar
- 21.Barakova, E., Zimmer, U.: Dynamic Situation and Trajectory Discrimination by Means of Clustering and Summation of Raw Range Data, AISTA, Australia (2000)Google Scholar